Score: inbound lead quality tier

The job

Jev judge eval (1 choice) over a fixed state : runnable via experimental_evaluate.

The prompt

Copy this into Muse and replace anything in [square brackets] with your own details.

// Score: inbound lead quality tier — Jev judge eval (typesafe-ai/jev).
// A demo request from a funded startup CTO; the judge tiers the lead.
// Model: typesafe-ai/jev via the Vercel AI Gateway ($0.042/1M input tokens).
// Auth: set AI_GATEWAY_API_KEY (vck_…) in the environment — never paste the key here.
// For zero-data-retention / no-training workloads, add
// providerOptions: { gateway: { … } } to the evaluate call below.

import { experimental_evaluate } from 'ai';

const result = await experimental_evaluate({
  model: 'typesafe-ai/jev',
  state: "Lead: CTO of a 120-person Series B startup, 40 engineers, evaluating for Q1 rollout. Budget approved, currently on a competitor, asked for security review docs and a pilot SOW.",
  questions: {
    "tier": {
      "type": "choice",
      "instructions": "Tier this lead by fit, authority, budget, and buying signals.",
      "criteria": {
        "hot": "Decision-maker, budget approved, timeline set, active evaluation.",
        "warm": "Good fit but missing authority, budget, or a clear timeline.",
        "cold": "Poor fit, no authority, or merely browsing with no intent."
      }
    }
  },
});

console.log(JSON.stringify(result, null, 2));